Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundaries
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908697916080128 |
|---|---|
| author | Xu, Wei Wagner, Charles James Luo, Junjie Guo, Qi |
| author_facet | Xu, Wei Wagner, Charles James Luo, Junjie Guo, Qi |
| contents | Extracting depth information from photon-limited, defocused images is challenging because depth from defocus (DfD) relies on accurate estimation of defocus blur, which is fundamentally sensitive to image noise. We present a novel approach to robustly measure object depths from photon-limited images along the defocused boundaries. It is based on a new image patch representation, Blurry-Edges, that explicitly stores and visualizes a rich set of low-level patch information, including boundaries, color, and smoothness. We develop a deep neural network architecture that predicts the Blurry-Edges representation from a pair of differently defocused images, from which depth can be calculated using a closed-form DfD relation we derive. The experimental results on synthetic and real data show that our method achieves the highest depth estimation accuracy on photon-limited images compared to a broad range of state-of-the-art DfD methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23606 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundaries Xu, Wei Wagner, Charles James Luo, Junjie Guo, Qi Computer Vision and Pattern Recognition Extracting depth information from photon-limited, defocused images is challenging because depth from defocus (DfD) relies on accurate estimation of defocus blur, which is fundamentally sensitive to image noise. We present a novel approach to robustly measure object depths from photon-limited images along the defocused boundaries. It is based on a new image patch representation, Blurry-Edges, that explicitly stores and visualizes a rich set of low-level patch information, including boundaries, color, and smoothness. We develop a deep neural network architecture that predicts the Blurry-Edges representation from a pair of differently defocused images, from which depth can be calculated using a closed-form DfD relation we derive. The experimental results on synthetic and real data show that our method achieves the highest depth estimation accuracy on photon-limited images compared to a broad range of state-of-the-art DfD methods. |
| title | Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundaries |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.23606 |